{"id":"https://openalex.org/W2904546325","doi":"https://doi.org/10.1109/ciss.2019.8692918","title":"Combatting Adversarial Attacks through Denoising and Dimensionality Reduction: A Cascaded Autoencoder Approach","display_name":"Combatting Adversarial Attacks through Denoising and Dimensionality Reduction: A Cascaded Autoencoder Approach","publication_year":2019,"publication_date":"2019-03-01","ids":{"openalex":"https://openalex.org/W2904546325","doi":"https://doi.org/10.1109/ciss.2019.8692918","mag":"2904546325"},"language":"en","primary_location":{"id":"doi:10.1109/ciss.2019.8692918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss.2019.8692918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1812.03087","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084897218","display_name":"Rajeev Sahay","orcid":"https://orcid.org/0000-0001-6823-1364"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Rajeev Sahay","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University","School of Electrical & Computer Engineering, Purdue University"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University","institution_ids":[]},{"raw_affiliation_string":"School of Electrical & Computer Engineering, Purdue University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037744622","display_name":"Rehana Mahfuz","orcid":"https://orcid.org/0000-0002-9974-1137"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rehana Mahfuz","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University","School of Electrical & Computer Engineering, Purdue University"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University","institution_ids":[]},{"raw_affiliation_string":"School of Electrical & Computer Engineering, Purdue University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051018107","display_name":"Aly El Gamal","orcid":"https://orcid.org/0000-0002-0400-4506"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aly El Gamal","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University","School of Electrical & Computer Engineering, Purdue University"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University","institution_ids":[]},{"raw_affiliation_string":"School of Electrical & Computer Engineering, Purdue University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084897218"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2893,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.64327526,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11515","display_name":"Bacillus and Francisella bacterial research","score":0.9553999900817871,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.9074236154556274},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.7141655087471008},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7101057767868042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.641398012638092},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5641655325889587},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5240254998207092},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5201714038848877},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5201418995857239},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4694475829601288},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.45826297998428345},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4437127113342285},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.43912646174430847},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38155505061149597}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9074236154556274},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.7141655087471008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7101057767868042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.641398012638092},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5641655325889587},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5240254998207092},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5201714038848877},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5201418995857239},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4694475829601288},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.45826297998428345},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4437127113342285},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.43912646174430847},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38155505061149597},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ciss.2019.8692918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss.2019.8692918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1812.03087","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.03087","pdf_url":"https://arxiv.org/pdf/1812.03087","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2904546325","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1812.03087","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1812.03087","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1812.03087","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1812.03087","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1812.03087","pdf_url":"https://arxiv.org/pdf/1812.03087","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2904546325.pdf","grobid_xml":"https://content.openalex.org/works/W2904546325.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1883420340","https://openalex.org/W2007562169","https://openalex.org/W2057803493","https://openalex.org/W2080565523","https://openalex.org/W2095577883","https://openalex.org/W2117130368","https://openalex.org/W2159607295","https://openalex.org/W2243397390","https://openalex.org/W2528914598","https://openalex.org/W2747237166","https://openalex.org/W2784285928"],"related_works":["https://openalex.org/W2963895533","https://openalex.org/W3099103512","https://openalex.org/W3009556147","https://openalex.org/W2753626192","https://openalex.org/W2733732820","https://openalex.org/W2963771536","https://openalex.org/W3090717570","https://openalex.org/W3109321589","https://openalex.org/W2886776264","https://openalex.org/W3134376291","https://openalex.org/W3089152679","https://openalex.org/W3127986341","https://openalex.org/W2890038638","https://openalex.org/W2995972302","https://openalex.org/W2292560765","https://openalex.org/W3161599138","https://openalex.org/W2947802941","https://openalex.org/W3104911906","https://openalex.org/W2971018118","https://openalex.org/W2972440122"],"abstract_inverted_index":{"Machine":[0],"Learning":[1],"models":[2],"are":[3],"vulnerable":[4],"to":[5,26,51],"adversarial":[6,93,129],"attacks":[7],"that":[8],"rely":[9],"on":[10],"perturbing":[11],"the":[12,42,53,68,71,75,90,103,112,125,128],"input":[13],"data.":[14,64],"This":[15],"work":[16],"proposes":[17],"a":[18,28,119],"novel":[19],"strategy":[20],"using":[21,74,108],"Autoencoder":[22],"Deep":[23],"Neural":[24],"Networks":[25],"defend":[27],"machine":[29],"learning":[30],"model":[31],"against":[32],"two":[33],"gradient-based":[34],"attacks:":[35],"The":[36],"Fast":[37,43],"Gradient":[38,44],"Sign":[39],"attack":[40],"and":[41,62,95],"attack.":[45],"First":[46],"we":[47,66],"use":[48],"an":[49],"autoencoder":[50],"denoise":[52],"test":[54,104],"data,":[55],"which":[56],"is":[57,106],"trained":[58],"with":[59],"both":[60],"clean":[61],"corrupted":[63],"Then,":[65],"reduce":[67],"dimension":[69],"of":[70,79,89,92,99,127],"denoised":[72],"data":[73,105],"hidden":[76],"layer":[77],"representation":[78],"another":[80],"autoencoder.":[81],"We":[82],"perform":[83],"this":[84,109],"experiment":[85],"for":[86],"multiple":[87],"values":[88],"bound":[91],"perturbations,":[94],"consider":[96],"different":[97],"numbers":[98],"reduced":[100],"dimensions.":[101],"When":[102],"preprocessed":[107],"cascaded":[110],"pipeline,":[111],"tested":[113],"deep":[114],"neural":[115],"network":[116],"classifier":[117],"yields":[118],"much":[120],"higher":[121],"accuracy,":[122],"thus":[123],"mitigating":[124],"effect":[126],"perturbation.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}